Triple

T5353762
Position Surface form Disambiguated ID Type / Status
Subject Maharana Pratap Sagar E102637 entity
Predicate nearestCity P350 FINISHED
Object Kangra E336927 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Kangra | Statement: [Maharana Pratap Sagar, nearestCity, Kangra]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kangra
Context triple: [Maharana Pratap Sagar, nearestCity, Kangra]
  • A. Kangra Valley chosen
    Kangra Valley is a picturesque valley in the Indian state of Himachal Pradesh, renowned for its lush landscapes, tea gardens, and views of the Dhauladhar mountain range.
  • B. Titagarh
    Titagarh is an industrial town in the North 24 Parganas district of eastern India, known historically for its jute mills and proximity to Kolkata.
  • C. Nurpur
    Nurpur is a historic town in the Kangra district of Himachal Pradesh, India, known for its ancient fort and temples amid scenic Himalayan foothills.
  • D. Kullu
    Kullu is a picturesque town in northern India’s Himalayas, known for its scenic valley, adventure tourism, and vibrant Dussehra festival.
  • E. Khaplu
    Khaplu is a historic town in northern Pakistan’s Gilgit-Baltistan region, known as a gateway to the Karakoram mountains and for its traditional Balti culture and architecture.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69bd43d8f7248190b64c140734b5c9a8 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd86149774819084049a8785e3f2e0 completed March 20, 2026, 5:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf4873ff0881908390c12767e18bb5 completed March 22, 2026, 1:40 a.m.
Created at: March 20, 2026, 2:01 p.m.